Polina Golland
Inaugural Sunlin (1996) and Priscilla Chou Professor, Department of Electrical Engineering and Computer Science

Polina Golland is the Inaugural Sunlin (1996) and Priscilla Chou Professor in MIT’s Department of Electrical Engineering and Computer Science. She leads the Medical Vision Group at the Computer Science and Artificial Intelligence Laboratory. Her main research focus is in developing novel techniques for analyzing and understanding biomedical images. Her interests include algorithms that explore the geometry of the world, process images in new ways and improve image-based inference through statistical modeling of image data. She is interested in shape modeling and representation, predictive modeling and visualization of statistical models. Her current research focuses on developing statistical methods for analyzing and characterizing biological processes based on image information. She earned a PhD in electrical engineering and computer science from MIT.
Selected Publications
- Abulnaga, S.M., Stein, O., Golland, P., Solomon, J. (2023). Symmetric Volume Maps: Order-Invariant Volumetric Mesh Correspondence with Free Boundary. ACM SIGGRAPH 2023.
- Abulnaga, S.M., Young, S. I., Hobgood, K., Pan, E., Wang, C. J., Grant, P. E., Abaci Turk, E., Golland, P. (2022) Automatic Segmentation of the Placenta in BOLD MRI Time Series. Perinatal, Preterm and Paediatric Image Analysis: 7th International Workshop, PIPPI 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022, ProceedingsSep 2022Pages 1–12https://doi.org/10.1007/978-3-031-17117-8_1
- Liao, R. et al. (2021). Multimodal Representation Learning via Maximization of Local Mutual Information. In: , et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12902. Springer, Cham. https://doi.org/10.1007/978-3-030-87196-3_26
Media
- October 2, 2019: MIT News, Using algorithms to build a map of the placenta.
- Jne 20, 2017: MIT News, New technique makes brain scans better.